© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83815
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to functions and features of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faithful
    -0.06
    ÚĨÛĮ
    -0.06
    appa
    -0.06
    iego
    -0.06
    ymb
    -0.06
    electronics
    -0.06
    ãn
    -0.06
     Bare
    -0.06
    022
    -0.06
    .getSelection
    -0.06
    POSITIVE LOGITS
    ONO
    0.07
    REFERRED
    0.07
    ROLS
    0.07
    olars
    0.06
    sov
    0.06
    hlen
    0.06
    rzy
    0.06
    steller
    0.06
     FEATURES
    0.06
    PERT
    0.06
    Activations Density 0.026%

    No Known Activations